论文标题
Mononhr：单眼神经人类渲染器
MonoNHR: Monocular Neural Human Renderer
论文作者
论文摘要
现有的神经人类渲染方法与单个图像输入相比，由于看不见的区域缺乏信息以及可见区域中像素的深度模棱两可。在这方面，我们提出了单眼神经人类渲染器（Mononhr），这是一种新颖的方法，它仅给出了单个图像的任意人类的稳健自由观看图像。 Mononhr是（i）使人类受试者在单眼设置中从未见过的第一种方法，并且（ii）在没有几何学监督的情况下以弱监督的方式进行训练。首先，我们建议解散3D几何和纹理特征，并调节3D几何特征的纹理推断。其次，我们介绍了一个网格的涂料模块，该模块对开发人类结构先验的遮挡部分（例如对称性）。关于ZJU-MOCAP，AIST和HUMBI数据集的实验表明，我们的方法显着优于最新方法适应于单眼病例。
Existing neural human rendering methods struggle with a single image input due to the lack of information in invisible areas and the depth ambiguity of pixels in visible areas. In this regard, we propose Monocular Neural Human Renderer (MonoNHR), a novel approach that renders robust free-viewpoint images of an arbitrary human given only a single image. MonoNHR is the first method that (i) renders human subjects never seen during training in a monocular setup, and (ii) is trained in a weakly-supervised manner without geometry supervision. First, we propose to disentangle 3D geometry and texture features and to condition the texture inference on the 3D geometry features. Second, we introduce a Mesh Inpainter module that inpaints the occluded parts exploiting human structural priors such as symmetry. Experiments on ZJU-MoCap, AIST, and HUMBI datasets show that our approach significantly outperforms the recent methods adapted to the monocular case.
